Hugging Face's logo

davanstrien
/
conditional-detr-resnet-50_fine_tuned_beyond_words

Object Detection
Transformers
PyTorch
TensorBoard
conditional_detr
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
davanstrien HF staff commited on
Commit
7481a01
•
1 Parent(s): e7d6ba8

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +160 -0
README.md ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - loc_beyond_words
7
+ model-index:
8
+ - name: conditional-detr-resnet-50_fine_tuned_beyond_words
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # conditional-detr-resnet-50_fine_tuned_beyond_words
16
+
17
+ This model is a fine-tuned version of [microsoft/conditional-detr-resnet-50](https://huggingface.co/microsoft/conditional-detr-resnet-50) on the loc_beyond_words dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.5892
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 200
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:-----:|:---------------:|
51
+ | 6.674 | 0.28 | 100 | 1.7571 |
52
+ | 1.4721 | 0.56 | 200 | 1.2737 |
53
+ | 1.2557 | 0.84 | 300 | 1.1037 |
54
+ | 1.0781 | 1.12 | 400 | 1.0184 |
55
+ | 1.0353 | 1.4 | 500 | 0.9988 |
56
+ | 1.0324 | 1.69 | 600 | 0.9951 |
57
+ | 0.9131 | 1.97 | 700 | 0.9224 |
58
+ | 0.8724 | 2.25 | 800 | 0.9692 |
59
+ | 0.8129 | 2.53 | 900 | 0.8670 |
60
+ | 0.9 | 2.81 | 1000 | 0.8326 |
61
+ | 0.7993 | 3.09 | 1100 | 0.7875 |
62
+ | 0.7907 | 3.37 | 1200 | 0.7517 |
63
+ | 0.8424 | 3.65 | 1300 | 0.9088 |
64
+ | 0.7808 | 3.93 | 1400 | 0.8506 |
65
+ | 0.7469 | 4.21 | 1500 | 0.7928 |
66
+ | 0.7582 | 4.49 | 1600 | 0.7228 |
67
+ | 0.7546 | 4.78 | 1700 | 0.7588 |
68
+ | 0.7842 | 5.06 | 1800 | 0.7726 |
69
+ | 0.775 | 5.34 | 1900 | 0.7676 |
70
+ | 0.7263 | 5.62 | 2000 | 0.7164 |
71
+ | 0.7209 | 5.9 | 2100 | 0.7061 |
72
+ | 0.7259 | 6.18 | 2200 | 0.7579 |
73
+ | 0.7701 | 6.46 | 2300 | 0.8184 |
74
+ | 0.7391 | 6.74 | 2400 | 0.6684 |
75
+ | 0.6834 | 7.02 | 2500 | 0.7042 |
76
+ | 0.7098 | 7.3 | 2600 | 0.7166 |
77
+ | 0.7498 | 7.58 | 2700 | 0.6752 |
78
+ | 0.7056 | 7.87 | 2800 | 0.7064 |
79
+ | 0.7004 | 8.15 | 2900 | 0.7090 |
80
+ | 0.6964 | 8.43 | 3000 | 0.7318 |
81
+ | 0.682 | 8.71 | 3100 | 0.7216 |
82
+ | 0.7309 | 8.99 | 3200 | 0.6545 |
83
+ | 0.6576 | 9.27 | 3300 | 0.6478 |
84
+ | 0.7014 | 9.55 | 3400 | 0.6814 |
85
+ | 0.673 | 9.83 | 3500 | 0.6783 |
86
+ | 0.6455 | 10.11 | 3600 | 0.7248 |
87
+ | 0.7041 | 10.39 | 3700 | 0.7729 |
88
+ | 0.6664 | 10.67 | 3800 | 0.6746 |
89
+ | 0.6161 | 10.96 | 3900 | 0.6414 |
90
+ | 0.6975 | 11.24 | 4000 | 0.6637 |
91
+ | 0.6751 | 11.52 | 4100 | 0.6570 |
92
+ | 0.6092 | 11.8 | 4200 | 0.6691 |
93
+ | 0.6593 | 12.08 | 4300 | 0.6276 |
94
+ | 0.6449 | 12.36 | 4400 | 0.6388 |
95
+ | 0.6136 | 12.64 | 4500 | 0.6711 |
96
+ | 0.6521 | 12.92 | 4600 | 0.6768 |
97
+ | 0.6162 | 13.2 | 4700 | 0.6427 |
98
+ | 0.7083 | 13.48 | 4800 | 0.6492 |
99
+ | 0.6407 | 13.76 | 4900 | 0.6213 |
100
+ | 0.6371 | 14.04 | 5000 | 0.6674 |
101
+ | 0.626 | 14.33 | 5100 | 0.6185 |
102
+ | 0.6442 | 14.61 | 5200 | 0.7180 |
103
+ | 0.5981 | 14.89 | 5300 | 0.6441 |
104
+ | 0.629 | 15.17 | 5400 | 0.6262 |
105
+ | 0.625 | 15.45 | 5500 | 0.6397 |
106
+ | 0.6123 | 15.73 | 5600 | 0.6440 |
107
+ | 0.6084 | 16.01 | 5700 | 0.6493 |
108
+ | 0.6021 | 16.29 | 5800 | 0.6263 |
109
+ | 0.6502 | 16.57 | 5900 | 0.6254 |
110
+ | 0.6339 | 16.85 | 6000 | 0.7043 |
111
+ | 0.5925 | 17.13 | 6100 | 0.8014 |
112
+ | 0.6453 | 17.42 | 6200 | 0.6385 |
113
+ | 0.6143 | 17.7 | 6300 | 0.6033 |
114
+ | 0.6057 | 17.98 | 6400 | 0.6881 |
115
+ | 0.6386 | 18.26 | 6500 | 0.6366 |
116
+ | 0.5839 | 18.54 | 6600 | 0.6563 |
117
+ | 0.6013 | 18.82 | 6700 | 0.5982 |
118
+ | 0.5999 | 19.1 | 6800 | 0.6064 |
119
+ | 0.6023 | 19.38 | 6900 | 0.5795 |
120
+ | 0.5593 | 19.66 | 7000 | 0.6538 |
121
+ | 0.6375 | 19.94 | 7100 | 0.6991 |
122
+ | 0.6073 | 20.22 | 7200 | 0.7117 |
123
+ | 0.596 | 20.51 | 7300 | 0.6034 |
124
+ | 0.5987 | 20.79 | 7400 | 0.6489 |
125
+ | 0.5922 | 21.07 | 7500 | 0.6216 |
126
+ | 0.589 | 21.35 | 7600 | 0.6257 |
127
+ | 0.6047 | 21.63 | 7700 | 0.6415 |
128
+ | 0.5775 | 21.91 | 7800 | 0.6159 |
129
+ | 0.588 | 22.19 | 7900 | 0.6095 |
130
+ | 0.5844 | 22.47 | 8000 | 0.6373 |
131
+ | 0.5964 | 22.75 | 8100 | 0.6022 |
132
+ | 0.5987 | 23.03 | 8200 | 0.6050 |
133
+ | 0.5605 | 23.31 | 8300 | 0.6083 |
134
+ | 0.5835 | 23.6 | 8400 | 0.7823 |
135
+ | 0.5816 | 23.88 | 8500 | 0.6417 |
136
+ | 0.5757 | 24.16 | 8600 | 0.6324 |
137
+ | 0.5997 | 24.44 | 8700 | 0.6046 |
138
+ | 0.5674 | 24.72 | 8800 | 0.6558 |
139
+ | 0.5703 | 25.0 | 8900 | 0.5819 |
140
+ | 0.5766 | 25.28 | 9000 | 0.6116 |
141
+ | 0.5548 | 25.56 | 9100 | 0.5877 |
142
+ | 0.564 | 25.84 | 9200 | 0.5672 |
143
+ | 0.548 | 26.12 | 9300 | 0.6073 |
144
+ | 0.5436 | 26.4 | 9400 | 0.5739 |
145
+ | 0.6006 | 26.69 | 9500 | 0.6101 |
146
+ | 0.5519 | 26.97 | 9600 | 0.5869 |
147
+ | 0.5432 | 27.25 | 9700 | 0.5721 |
148
+ | 0.5597 | 27.53 | 9800 | 0.5807 |
149
+ | 0.5254 | 27.81 | 9900 | 0.5849 |
150
+ | 0.5366 | 28.09 | 10000 | 0.5831 |
151
+ | 0.5654 | 28.37 | 10100 | 0.5993 |
152
+ | 0.57 | 28.65 | 10200 | 0.5892 |
153
+
154
+
155
+ ### Framework versions
156
+
157
+ - Transformers 4.26.1
158
+ - Pytorch 1.13.0+cu117
159
+ - Datasets 2.10.1
160
+ - Tokenizers 0.13.2